Official documentation
canary-1b model card (raw README)
NVIDIA, Hugging Face (NVIDIA model card), n.d.
Read the originalRead on October 19, 2026
- What it is
- NVIDIA's model card for Canary 1B, read from its raw README. It gives word error rate on Mozilla Common Voice 16.1 and Multilingual LibriSpeech for English, German, Spanish and French.
- How much weight it carries
- Self-reported by NVIDIA, the model developer. The card uses its own text normalization and decoding, so its figures are not directly comparable with other vendors' full-transcript scores. Compare only within the same test set.
Facts taken from this source
- NVIDIA Canary 1B had a word error rate of 4.61 percent on Common Voice German.
“WER on [MCV-16.1](https://commonvoice.mozilla.org/en/datasets) test set: | **Version** | **Model** | **En** | **De** | **Es** | **Fr** | ... | 1.23.0 | canary-1b | 7.97 | 4.61 | 3.99 | 6.53 |” (WER table, de column)
- NVIDIA Canary 1B had a word error rate of 7.97 percent on Common Voice English.
“WER on [MCV-16.1](https://commonvoice.mozilla.org/en/datasets) test set: | **Version** | **Model** | **En** | **De** | **Es** | **Fr** | ... | 1.23.0 | canary-1b | 7.97 | 4.61 | 3.99 | 6.53 |” (WER table, en column)
- NVIDIA Canary 1B had a word error rate of 3.99 percent on Common Voice Spanish.
“WER on [MCV-16.1](https://commonvoice.mozilla.org/en/datasets) test set: | **Version** | **Model** | **En** | **De** | **Es** | **Fr** | ... | 1.23.0 | canary-1b | 7.97 | 4.61 | 3.99 | 6.53 |” (WER table, es column)
- NVIDIA Canary 1B had a word error rate of 6.53 percent on Common Voice French.
“WER on [MCV-16.1](https://commonvoice.mozilla.org/en/datasets) test set: | **Version** | **Model** | **En** | **De** | **Es** | **Fr** | ... | 1.23.0 | canary-1b | 7.97 | 4.61 | 3.99 | 6.53 |” (WER table, fr column)
- NVIDIA Canary 1B had a word error rate of 4.19 percent on Multilingual LibriSpeech German.
“WER on [MLS](https://huggingface.co/datasets/facebook/multilingual_librispeech) test set: | **Version** | **Model** | **En** | **De** | **Es** | **Fr** | ... | 1.23.0 | canary-1b | 3.06 | 4.19 | 3.15 | 4.12 |” (WER table, de column)
- NVIDIA Canary 1B had a word error rate of 3.06 percent on Multilingual LibriSpeech English.
“WER on [MLS](https://huggingface.co/datasets/facebook/multilingual_librispeech) test set: | **Version** | **Model** | **En** | **De** | **Es** | **Fr** | ... | 1.23.0 | canary-1b | 3.06 | 4.19 | 3.15 | 4.12 |” (WER table, en column)
- NVIDIA Canary 1B had a word error rate of 3.15 percent on Multilingual LibriSpeech Spanish.
“WER on [MLS](https://huggingface.co/datasets/facebook/multilingual_librispeech) test set: | **Version** | **Model** | **En** | **De** | **Es** | **Fr** | ... | 1.23.0 | canary-1b | 3.06 | 4.19 | 3.15 | 4.12 |” (WER table, es column)
- NVIDIA Canary 1B had a word error rate of 4.12 percent on Multilingual LibriSpeech French.
“WER on [MLS](https://huggingface.co/datasets/facebook/multilingual_librispeech) test set: | **Version** | **Model** | **En** | **De** | **Es** | **Fr** | ... | 1.23.0 | canary-1b | 3.06 | 4.19 | 3.15 | 4.12 |” (WER table, fr column)